© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 3730
    Prev
    Next
    INDEX
    Explanations

    references to official organizations and their activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bicchiere
    -0.67
     frattempo
    -0.63
     cervello
    -0.63
     paesaggio
    -0.59
     benessere
    -0.58
     quartiere
    -0.57
     tramonto
    -0.56
     linguaggio
    -0.56
     discorso
    -0.56
     ritratto
    -0.54
    POSITIVE LOGITS
     Caro
    0.68
    Caro
    0.68
     Mero
    0.66
     Milo
    0.65
     Duro
    0.62
     Vero
    0.61
     Waldo
    0.60
     Maro
    0.60
     Viro
    0.60
     Leto
    0.59
    Activations Density 1.301%

    No Known Activations